Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 858
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to technology, often including the word "type"

    oai_token-act-pair · gemini-2.0-flash

    technical applications and usage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.53
    
    -0.51
    makeConstraints
    -0.50
     =>
    -0.49
    IsMutable
    -0.47
    Eventually
    -0.47
     frontale
    -0.46
    adaptiveStyles
    -0.46
     <=",
    -0.46
     propOrder
    -0.45
    POSITIVE LOGITS
    <bos>
    0.65
    tvguidetime
    0.64
     SafeMath
    0.61
    UserScript
    0.60
    帖最后由
    0.58
     snippetHide
    0.57
     freie
    0.54
     freien
    0.54
    DockStyle
    0.50
     imposing
    0.50
    Activations Density 45.570%

    No Known Activations